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

    Neuronpedia

    INDEX
    Explanations

    instances where something is dependent or based on certain conditions

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases that express variability based on circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    boa
    -0.66
    çĦ
    -0.65
    boro
    -0.60
    itsch
    -0.60
    ç«
    -0.59
     Yad
    -0.59
    DER
    -0.58
    76561
    -0.58
    elta
    -0.58
    tsky
    -0.57
    POSITIVE LOGITS
     upon
    1.10
     how
    0.86
     on
    0.85
     critically
    0.82
     depending
    0.81
     whether
    0.80
     Upon
    0.71
    ersed
    0.70
     if
    0.69
     entirely
    0.69
    Act Density 0.023%

    No Known Activations