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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" and associated verbs indicating actions or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hdashline
    -0.80
     activer
    -0.74
    flame
    -0.72
     vang
    -0.72
    PRWEB
    -0.71
    Pratique
    -0.71
    ſelves
    -0.69
    almaz
    -0.69
    OLOGIA
    -0.69
     gethan
    -0.69
    POSITIVE LOGITS
     must
    1.12
    Gotta
    1.10
     Gotta
    1.03
     gotta
    1.00
    Must
    0.95
     be
    0.92
     Must
    0.90
     måste
    0.88
     MUST
    0.85
     doit
    0.84
    Act Density 0.106%

    No Known Activations