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

    Neuronpedia

    INDEX
    Explanations

    instances of the infinitive form “to” followed by a verb

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gethan
    -0.82
    เอง
    -0.77
    almaz
    -0.77
     zelve
    -0.75
     Grecs
    -0.74
     Yap
    -0.73
     souten
    -0.71
     zijne
    -0.71
     erhi
    -0.71
     ainfi
    -0.70
    POSITIVE LOGITS
    Gotta
    1.16
     gotta
    1.06
     Gotta
    1.04
     be
    1.03
     propOrder
    0.92
     must
    0.87
    icoot
    0.83
    gotta
    0.83
     to
    0.83
    Muss
    0.81
    Act Density 0.072%

    No Known Activations