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

    Neuronpedia

    INDEX
    Explanations

    numerical values expressed as fractions or ratios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     himſelf
    -0.79
     myſelf
    -0.77
     Theſe
    -0.77
     InputDecoration
    -0.76
     themſelves
    -0.74
    qrstuvwxyz
    -0.73
     itſelf
    -0.69
    Demografie
    -0.68
    новниш
    -0.67
     theſe
    -0.66
    POSITIVE LOGITS
    SourceChecksum
    0.71
     prong
    0.68
    part
    0.66
     part
    0.65
     tiered
    0.57
    prong
    0.55
     phase
    0.53
     tier
    0.50
    tier
    0.50
    phase
    0.49
    Act Density 0.183%

    No Known Activations