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

    Neuronpedia

    INDEX
    Explanations

    references to inappropriate social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    indo
    -0.21
    oldem
    -0.15
    ramer
    -0.15
    zte
    -0.15
     AssemblyVersion
    -0.14
    straint
    -0.13
    auss
    -0.13
    incl
    -0.13
     incl
    -0.13
     anth
    -0.13
    POSITIVE LOGITS
    Enlarge
    0.16
    ient
    0.15
     воÑĢ
    0.15
     dod
    0.14
    ëįĺ
    0.14
    Ack
    0.14
    ingt
    0.14
    _ack
    0.13
    gado
    0.13
     parl
    0.13
    Act Density 0.000%

    No Known Activations