Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or objectives, especially those that involve bringing, creating, showing, spreading, raising, providing, making, giving, or holding

    oai_token-act-pair · gpt-3.5-turbo

    actions related to bringing attention or awareness to something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eyed
    -0.64
     Torn
    -0.63
     attached
    -0.63
     fret
    -0.62
     pse
    -0.61
     rumored
    -0.60
     preferring
    -0.60
     fearing
    -0.59
     incl
    -0.59
    Guard
    -0.59
    POSITIVE LOGITS
    uate
    0.87
    atform
    0.81
    edia
    0.78
    entious
    0.78
    imize
    0.76
    IENT
    0.75
     disruptive
    0.74
    igate
    0.73
     awareness
    0.73
     disruption
    0.70
    Act Density 0.375%

    No Known Activations