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

    Neuronpedia

    INDEX
    Explanations

    terms related to destruction or harmfulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allet
    -0.17
    ü
    -0.16
    ani
    -0.15
    eration
    -0.15
    uts
    -0.14
    صÙģ
    -0.14
    AndPassword
    -0.14
    joy
    -0.14
     turb
    -0.14
    itol
    -0.14
    POSITIVE LOGITS
    matcher
    0.16
    yw
    0.15
    orce
    0.15
    ingham
    0.15
    268
    0.14
    ÚĺÙĨ
    0.14
    IID
    0.14
    deaux
    0.13
    ög
    0.13
    oral
    0.13
    Act Density 0.001%

    No Known Activations