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

    Neuronpedia

    INDEX
    Explanations

    phrases related to investments or changes in value

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the effects or outcomes of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iege
    -0.71
    ridge
    -0.65
    amiya
    -0.65
     Madness
    -0.61
     Vide
    -0.60
     Britann
    -0.60
     Container
    -0.60
    heid
    -0.59
     Ruler
    -0.57
     Oaks
    -0.57
    POSITIVE LOGITS
     rid
    1.18
    tin
    0.81
    TING
    0.81
     underway
    0.78
    gets
    0.78
     bog
    0.76
    ãĥ³ãĤ¸
    0.76
     progressively
    0.76
    terson
    0.72
     precedence
    0.71
    Act Density 0.125%

    No Known Activations