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

    Neuronpedia

    INDEX
    Explanations

    sentences related to objectives or goals

    oai_token-act-pair · gpt-3.5-turbo

    terms related to goals and objectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    liv
    -0.59
    ãģĦ
    -0.59
    culus
    -0.58
    gettable
    -0.55
     Celtic
    -0.55
     jaws
    -0.55
     unequ
    -0.54
    RIP
    -0.53
     cursing
    -0.53
     SIGN
    -0.53
    POSITIVE LOGITS
     is
    0.91
     was
    0.81
     boils
    0.75
     isn
    0.74
    fore
    0.73
     consists
    0.72
    goal
    0.71
     wasn
    0.71
     revolves
    0.71
     goal
    0.69
    Act Density 0.136%

    No Known Activations