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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific letters or combinations of letters

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'b' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eer
    -0.85
    eve
    -0.64
     fet
    -0.63
     contracted
    -0.63
    e
    -0.63
     bound
    -0.60
     credential
    -0.59
     organised
    -0.59
    OOL
    -0.59
     arming
    -0.59
    POSITIVE LOGITS
    esides
    1.00
    cm
    0.94
    reenshot
    0.94
    cd
    0.89
    redits
    0.89
    bsp
    0.82
    orthern
    0.81
    undreds
    0.81
    urther
    0.81
    terior
    0.81
    Act Density 0.097%

    No Known Activations