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

    Neuronpedia

    INDEX
    Explanations

    words related to reported actions or events

    oai_token-act-pair · gpt-3.5-turbo

    the word "reportedly" and its variants, indicating reported statements or claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etime
    -0.70
    ĸļ
    -0.69
    gers
    -0.68
    ERAL
    -0.65
    clusions
    -0.65
    ravel
    -0.65
    avascript
    -0.64
    CHECK
    -0.64
    allas
    -0.63
    lap
    -0.63
    POSITIVE LOGITS
     located
    0.79
     obtained
    0.77
     entertained
    0.75
     solic
    0.75
     priced
    0.73
     disposed
    0.71
     complied
    0.71
     overheard
    0.70
     originated
    0.69
     consulted
    0.69
    Act Density 0.029%

    No Known Activations