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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "enter" and its variants related to actions of entering or joining

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ghan
    -0.19
    venir
    -0.18
    zin
    -0.16
    usercontent
    -0.15
    arness
    -0.15
    imo
    -0.15
    stanbul
    -0.14
    orta
    -0.14
    uba
    -0.14
    InputChange
    -0.14
    POSITIVE LOGITS
    prising
    0.47
     into
    0.31
    prises
    0.29
    prisingly
    0.27
    into
    0.25
    /ex
    0.24
    preneur
    0.24
    PRI
    0.24
    prene
    0.24
     Into
    0.24
    Act Density 0.028%

    No Known Activations