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

    Neuronpedia

    INDEX
    Explanations

    words related to rumors and accusations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to suspicion or accusations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ien
    -0.74
    ouk
    -0.69
    atre
    -0.65
    pling
    -0.65
    oses
    -0.63
    sid
    -0.63
    idelines
    -0.62
    osures
    -0.61
    borg
    -0.61
    gur
    -0.60
    POSITIVE LOGITS
     arose
    0.80
     they
    0.78
    soever
    0.77
     accompanies
    0.73
     contradicts
    0.72
    warts
    0.71
     fateful
    0.71
    might
    0.68
    ndra
    0.68
     prompted
    0.67
    Act Density 0.220%

    No Known Activations