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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a sequence of actions or instructions

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "as follows" and its variations indicating enumerations or listings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    minist
    -0.73
    aukee
    -0.71
    irts
    -0.70
    cest
    -0.69
    Newsletter
    -0.67
    ozo
    -0.65
    obyl
    -0.65
    izont
    -0.64
    vae
    -0.63
    orio
    -0.62
    POSITIVE LOGITS
    :"
    1.03
    :-
    1.03
    >:
    0.93
    :
    0.92
    :'
    0.86
    :#
    0.84
    :{
    0.82
    :]
    0.81
    :(
    0.78
    —"
    0.78
    Act Density 0.029%

    No Known Activations