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

    Neuronpedia

    INDEX
    Explanations

    phrases related to objectives or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Franke
    -0.76
    ogeneous
    -0.73
     Peterson
    -0.66
    "}}
    -0.65
     Schroeder
    -0.65
    readFileSync
    -0.63
     McCarty
    -0.62
    ibouti
    -0.62
     The
    -0.61
     Platten
    -0.60
    POSITIVE LOGITS
     Aims
    1.63
     Aim
    1.58
     AIM
    1.53
    Aim
    1.47
    Aims
    1.45
    AIM
    1.38
    aim
    1.33
     aims
    1.33
     aim
    1.25
     aimed
    1.24
    Act Density 0.049%

    No Known Activations