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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating worsening conditions or negative situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heny
    -0.77
    ogens
    -0.75
    DX
    -0.73
    ebin
    -0.73
    ingu
    -0.71
    ocene
    -0.69
    odcast
    -0.68
    ogenous
    -0.68
    otal
    -0.67
    tnc
    -0.66
    POSITIVE LOGITS
     farther
    0.79
     faster
    0.78
     hotter
    0.76
     clearer
    0.76
     heavier
    0.75
     prett
    0.73
     louder
    0.69
     thicker
    0.69
     harder
    0.68
     quicker
    0.67
    Act Density 0.031%

    No Known Activations