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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to serious and consequential issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    prung
    -0.14
    undance
    -0.14
    ÑĤÑĥ
    -0.14
    pecies
    -0.13
    ilver
    -0.13
     Toe
    -0.13
    nger
    -0.13
    lesi
    -0.13
    rike
    -0.13
     Frem
    -0.13
    POSITIVE LOGITS
     effort
    0.76
     efforts
    0.66
     Eff
    0.58
    -eff
    0.49
    eff
    0.49
    Eff
    0.45
    åĬªåĬĽ
    0.42
    _eff
    0.40
     eff
    0.38
     EFF
    0.38
    Act Density 0.120%

    No Known Activations