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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "alleged" in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to alleged incidents or claims of wrongdoing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -0.73
     Clicker
    -0.71
    ARCH
    -0.70
    pb
    -0.69
    eyes
    -0.68
    OVA
    -0.66
    bern
    -0.65
    ajo
    -0.63
    beard
    -0.63
    patch
    -0.63
    POSITIVE LOGITS
    iary
    0.87
     allegations
    0.85
    ities
    0.85
     accusations
    0.79
     abuser
    0.78
     accuser
    0.77
    edly
    0.74
     misrepresent
    0.74
     violations
    0.72
     abuse
    0.72
    Act Density 0.025%

    No Known Activations