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

    Neuronpedia

    INDEX
    Explanations

    verbs related to giving instructions or guidance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "directed."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mell
    -0.72
    iddler
    -0.69
    isers
    -0.65
    ylon
    -0.64
     Sack
    -0.64
    Du
    -0.63
    iders
    -0.63
    Face
    -0.62
     Frag
    -0.62
     Sloven
    -0.62
    POSITIVE LOGITS
    irection
    0.93
    ovie
    0.89
     toward
    0.89
    irect
    0.89
     directed
    0.87
    htaking
    0.86
     towards
    0.83
     directing
    0.83
    eering
    0.81
    inarily
    0.81
    Act Density 0.019%

    No Known Activations