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

    Neuronpedia

    INDEX
    Explanations

    words related to hooks or hooking

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "hook" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ndum
    -0.75
    zza
    -0.74
    imens
    -0.71
     guiIcon
    -0.70
     Scotia
    -0.68
    cles
    -0.68
     Mandal
    -0.66
    ãĥ©ãĥ³
    -0.66
     Nieto
    -0.66
    ————
    -0.64
    POSITIVE LOGITS
    tail
    1.05
    tails
    0.99
    hook
    0.94
    pipe
    0.91
    notes
    0.90
    worm
    0.90
    hole
    0.89
    masters
    0.87
    back
    0.87
    worms
    0.87
    Act Density 0.036%

    No Known Activations