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

    Neuronpedia

    INDEX
    Explanations

    the word "Here" and its variations indicating the start of an important statement or idea

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.82
    ftagPool
    -0.76
     Réponses
    -0.75
    DockStyle
    -0.73
    ngrx
    -0.68
    twimg
    -0.67
    jspb
    -0.67
     betweenstory
    -0.67
    nalité
    -0.67
    offsetof
    -0.66
    POSITIVE LOGITS
    Here
    0.73
     Here
    0.70
     are
    0.61
    tical
    0.60
    here
    0.56
     here
    0.56
    ’
    0.55
    Heres
    0.55
    '
    0.53
     HERE
    0.53
    Act Density 0.058%

    No Known Activations