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

    Neuronpedia

    INDEX
    Explanations

    specific references to notable individuals or entities in a political or social context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    (&:
    -0.61
     apparently
    -0.56
    henswürdigkeiten
    -0.52
     ddelweddau
    -0.51
    ces
    -0.51
    gway
    -0.49
     almost
    -0.48
    enderror
    -0.47
    ضان
    -0.47
     absl
    -0.46
    POSITIVE LOGITS
    katapos
    0.64
     any
    0.56
    enumii
    0.53
     jemals
    0.53
    betical
    0.52
    akaan
    0.51
    WireFormatLite
    0.50
     berätt
    0.50
    ondos
    0.50
    省市镇
    0.50
    Act Density 0.205%

    No Known Activations