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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or decisions that need to be taken

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to actions that require effort or decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.72
    alde
    -0.70
    ¥µ
    -0.67
    luaj
    -0.67
    gnu
    -0.65
     Holo
    -0.63
     Emerging
    -0.63
    MpServer
    -0.63
    AAA
    -0.62
    unin
    -0.60
    POSITIVE LOGITS
     manually
    0.83
     somewhere
    0.82
     oneself
    0.80
    escription
    0.76
    dress
    0.74
     urgently
    0.74
     ASAP
    0.73
     reckon
    0.69
     something
    0.68
     lengths
    0.67
    Act Density 0.280%

    No Known Activations